— We propose a novel inertial-aided KLT feature tracking method robust to camera ego-motions. The conventional KLT uses images only and its working condition is inherently limite...
In this paper, we present a novel approach for human activities recognition in the video. We analyze human activities in the sequential frames because human activities can be cons...
We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific an...
In this paper, we present an automatic classification framework combining appearance based features and Hidden Markov Models (HMM) to detect unusual events in image sequences. One...
This paper proposes a method for detecting instances of shape classes that exhibit variable structure. The term "variable structure" is used to characterize shape classes...
Vassilis Athitsos, Jingbin Wang, Stan Sclaroff, Ma...